resolve-review-comments

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text from the PR/MR review threads (GitHub GraphQL pullRequest.reviewThreads with isResolved: false, and GitHub issue comments via REST issues/{pr}/comments / GitLab discussions) is fetched at runtime and then used for triage/implementation prompts, so it enters the agent’s LLM context indirectly as “full comment text”.